Merge branch 'master' into remove_the_batch_suffix_from_examples

.ci/pipeline/build-and-test-lnx.yml

@@ -24,7 +24,7 @@ steps:
     displayName: 'System info'
   - script: |
       conda update -y -q conda
-      if [ $(echo $(PYTHON_VERSION) | grep '3.7') ] || [ $(echo $(PYTHON_VERSION) | grep '3.11') ]; then export DPCPP_PACKAGE="dpcpp-cpp-rt>=2023.1.0"; else export DPCPP_PACKAGE="dpctl>=0.14 dpcpp-cpp-rt>=2023.1.0"; fi
+      if [ $(echo $(PYTHON_VERSION) | grep '3.7') ] || [ $(echo $(PYTHON_VERSION) | grep '3.11') ]; then export DPCPP_PACKAGE="dpcpp-cpp-rt>=2023.2.0"; else export DPCPP_PACKAGE="dpctl>=0.14 dpcpp-cpp-rt>=2023.2.0"; fi
       conda create -q -y -n CB -c conda-forge -c intel python=$(PYTHON_VERSION) dal-devel mpich pyyaml $DPCPP_PACKAGE
     displayName: 'Conda create'
   - script: |

.ci/pipeline/build-and-test-mac.yml

@@ -19,7 +19,7 @@ steps:
       sudo chown -R $USER $CONDA
       conda config --set always_yes yes --set changeps1 no
       conda update -q conda
-      conda create -n CB -c conda-forge python=$(PYTHON_VERSION) dal=2023.0.1 dal-include=2023.0.1 mpich clang-format pyyaml
+      conda create -n CB -c conda-forge python=$(PYTHON_VERSION) dal-devel mpich clang-format pyyaml
     displayName: Create Anaconda environment
   - script: |
       source activate CB

.ci/scripts/install_dpcpp.sh

@@ -21,6 +21,6 @@ rm GPG-PUB-KEY-INTEL-SW-PRODUCTS-2023.PUB
 echo "deb https://apt.repos.intel.com/oneapi all main" | sudo tee /etc/apt/sources.list.d/oneAPI.list
 sudo add-apt-repository -y "deb https://apt.repos.intel.com/oneapi all main"
 sudo apt-get update
-sudo apt-get install -y intel-dpcpp-cpp-compiler-2023.1.0
+sudo apt-get install -y intel-dpcpp-cpp-compiler-2023.2.0
 sudo bash -c 'echo libintelocl.so > /etc/OpenCL/vendors/intel-cpu.icd'
 sudo mv -f /opt/intel/oneapi/compiler/latest/linux/lib/oclfpga /opt/intel/oneapi/compiler/latest/linux/lib/oclfpga_

examples/daal4py/covariance_streaming.py

@@ -1,4 +1,4 @@
-#===============================================================================
+# ===============================================================================
 # Copyright 2014 Intel Corporation
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
@@ -12,17 +12,17 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-#===============================================================================
+# ===============================================================================
 
 # daal4py covariance example for streaming on shared memory systems
 
-import daal4py as d4p
-
 # let's use a generator for getting stream from file (defined in stream.py)
 from stream import read_next
 
+import daal4py as d4p
+
 
-def main(readcsv=None, method='defaultDense'):
+def main(readcsv=None, method="defaultDense"):
     infile = "./data/batch/covcormoments_dense.csv"
 
     # configure a covariance object
@@ -44,4 +44,4 @@ def main(readcsv=None, method='defaultDense'):
     res = main()
     print("Covariance matrix:\n", res.covariance)
     print("Mean vector:\n", res.mean)
-    print('All looks good!')
+    print("All looks good!")

examples/daal4py/dbscan_spmd.py

@@ -1,4 +1,4 @@
-#===============================================================================
+# ===============================================================================
 # Copyright 2014 Intel Corporation
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
@@ -12,25 +12,26 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-#===============================================================================
+# ===============================================================================
 
 # daal4py DBSCAN example for distributed memory systems; SPMD mode
 # run like this:
 #    mpirun -n 4 python ./dbscan_spmd.py
 
-import daal4py as d4p
 import numpy as np
 
+import daal4py as d4p
+
 
-def main(method='defaultDense'):
+def main(method="defaultDense"):
     infile = "./data/batch/dbscan_dense.csv"
     epsilon = 0.04
     minObservations = 45
 
     # Load the data
-    data = np.loadtxt(infile, delimiter=',')
+    data = np.loadtxt(infile, delimiter=",")
     rpp = int(data.shape[0] / d4p.num_procs())
-    data = data[rpp * d4p.my_procid(): rpp * d4p.my_procid() + rpp, :]
+    data = data[rpp * d4p.my_procid() : rpp * d4p.my_procid() + rpp, :]
 
     # configure dbscan main object
     algo = d4p.dbscan(minObservations=minObservations, epsilon=epsilon, distributed=True)
@@ -44,7 +45,13 @@ def main(method='defaultDense'):
     # Initialize SPMD mode
     d4p.daalinit()
     result = main()
-    print("\nResults on node with id = ", d4p.my_procid(), " :\n",
-          "\nFirst 10 cluster assignments:\n", result.assignments[0:10],
-          "\nNumber of clusters:\n", result.nClusters)
+    print(
+        "\nResults on node with id = ",
+        d4p.my_procid(),
+        " :\n",
+        "\nFirst 10 cluster assignments:\n",
+        result.assignments[0:10],
+        "\nNumber of clusters:\n",
+        result.nClusters,
+    )
     d4p.daalfini()

examples/daal4py/decision_forest_classification_traverse.py

@@ -22,6 +22,8 @@
 
 import daal4py as d4p
 
+import daal4py as d4p
+
 
 def printTree(nodes, values):
     def printNodes(node_id, nodes, values, level):

examples/daal4py/decision_forest_regression_traverse.py

@@ -22,6 +22,8 @@
 
 import daal4py as d4p
 
+import daal4py as d4p
+
 
 def printTree(nodes, values):
     def printNodes(node_id, nodes, values, level):

examples/daal4py/decision_tree_classification_traverse.py

@@ -22,6 +22,8 @@
 
 import daal4py as d4p
 
+import daal4py as d4p
+
 
 def printTree(nodes, values):
     def printNodes(node_id, nodes, values, level):

examples/daal4py/decision_tree_regression_traverse.py

@@ -22,6 +22,8 @@
 
 import daal4py as d4p
 
+import daal4py as d4p
+
 
 def printTree(nodes, values):
     def printNodes(node_id, nodes, values, level):

examples/daal4py/gradient_boosted_classification_traverse.py

@@ -22,6 +22,8 @@
 
 import daal4py as d4p
 
+import daal4py as d4p
+
 
 def printTree(nodes, values):
     def printNodes(node_id, nodes, values, level):

examples/daal4py/gradient_boosted_regression_traverse.py

@@ -22,6 +22,8 @@
 
 import daal4py as d4p
 
+import daal4py as d4p
+
 
 def printTree(nodes, values):
     def printNodes(node_id, nodes, values, level):

examples/daal4py/kmeans_spmd.py

@@ -1,4 +1,4 @@
-#===============================================================================
+# ===============================================================================
 # Copyright 2014 Intel Corporation
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
@@ -12,29 +12,30 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-#===============================================================================
+# ===============================================================================
 
 # daal4py K-Means example for distributed memory systems; SPMD mode
 # run like this:
 #    mpirun -n 4 python ./kmeans_spmd.py
 
-import daal4py as d4p
 from numpy import loadtxt
 
+import daal4py as d4p
+
 
-def main(method='plusPlusDense'):
+def main(method="plusPlusDense"):
     infile = "./data/distributed/kmeans_dense.csv"
     nClusters = 10
     maxIter = 25
 
     # configure a kmeans-init
     init_algo = d4p.kmeans_init(nClusters, method=method, distributed=True)
     # Load the data
-    data = loadtxt(infile, delimiter=',')
+    data = loadtxt(infile, delimiter=",")
     # now slice the data,
     # it would have been better to read only what we need, of course...
     rpp = int(data.shape[0] / d4p.num_procs())
-    data = data[rpp * d4p.my_procid(): rpp * d4p.my_procid() + rpp, :]
+    data = data[rpp * d4p.my_procid() : rpp * d4p.my_procid() + rpp, :]
 
     # compute initial centroids
     init_result = init_algo.compute(data)
@@ -78,5 +79,5 @@ def main(method='plusPlusDense'):
         print("\nFirst 10 cluster assignments:\n", assignments[0:10])
         print("\nFirst 10 dimensions of centroids:\n", result.centroids[:, 0:10])
         print("\nObjective function value:\n", result.objectiveFunction)
-        print('All looks good!')
+        print("All looks good!")
     d4p.daalfini()

examples/daal4py/linear_regression_spmd.py

@@ -1,4 +1,4 @@
-#===============================================================================
+# ===============================================================================
 # Copyright 2014 Intel Corporation
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
@@ -12,30 +12,32 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-#===============================================================================
+# ===============================================================================
 
 # daal4py Linear Regression example for distributed memory systems; SPMD mode
 # run like this:
 #    mpirun -n 4 python ./linreg_spmd.py
 
-import daal4py as d4p
 from numpy import loadtxt
 
+import daal4py as d4p
+
 if __name__ == "__main__":
     # Initialize SPMD mode
     d4p.daalinit()
 
     # Each process gets its own data
-    infile = "./data/distributed/linear_regression_train_" + \
-        str(d4p.my_procid() + 1) + ".csv"
+    infile = (
+        "./data/distributed/linear_regression_train_" + str(d4p.my_procid() + 1) + ".csv"
+    )
 
     # Configure a Linear regression training object
     train_algo = d4p.linear_regression_training(distributed=True)
 
     # Read data. Let's have 10 independent,
     # and 2 dependent variables (for each observation)
-    indep_data = loadtxt(infile, delimiter=',', usecols=range(10))
-    dep_data = loadtxt(infile, delimiter=',', usecols=range(10, 12))
+    indep_data = loadtxt(infile, delimiter=",", usecols=range(10))
+    dep_data = loadtxt(infile, delimiter=",", usecols=range(10, 12))
     # Now train/compute, the result provides the model for prediction
     train_result = train_algo.compute(indep_data, dep_data)
 
@@ -44,14 +46,18 @@
     if d4p.my_procid() == 0:
         predict_algo = d4p.linear_regression_prediction()
         # read test data (with same #features)
-        pdata = loadtxt("./data/distributed/linear_regression_test.csv",
-                        delimiter=',', usecols=range(10))
+        pdata = loadtxt(
+            "./data/distributed/linear_regression_test.csv",
+            delimiter=",",
+            usecols=range(10),
+        )
         # now predict using the model from the training above
-        predict_result = d4p.linear_regression_prediction().compute(pdata,
-                                                                    train_result.model)
+        predict_result = d4p.linear_regression_prediction().compute(
+            pdata, train_result.model
+        )
 
         # The prediction result provides prediction
         assert predict_result.prediction.shape == (pdata.shape[0], dep_data.shape[1])
 
-    print('All looks good!')
+    print("All looks good!")
     d4p.daalfini()

examples/daal4py/linear_regression_streaming.py

@@ -1,4 +1,4 @@
-#===============================================================================
+# ===============================================================================
 # Copyright 2014 Intel Corporation
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
@@ -12,32 +12,35 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-#===============================================================================
+# ===============================================================================
 
 # daal4py Linear Regression example for streaming on shared memory systems
 
-import daal4py as d4p
 import numpy as np
 
+import daal4py as d4p
+
 # let's try to use pandas' fast csv reader
 try:
     import pandas
 
     def read_csv(f, c, s=0, n=None, t=np.float64):
-        return pandas.read_csv(f, usecols=c, delimiter=',', header=None,
-                               skiprows=s, nrows=n, dtype=t)
+        return pandas.read_csv(
+            f, usecols=c, delimiter=",", header=None, skiprows=s, nrows=n, dtype=t
+        )
+
 except:
     # fall back to numpy genfromtxt
     def read_csv(f, c, s=0, n=np.iinfo(np.int64).max):
-        a = np.genfromtxt(f, usecols=c, delimiter=',', skip_header=s, max_rows=n)
+        a = np.genfromtxt(f, usecols=c, delimiter=",", skip_header=s, max_rows=n)
         if a.shape[0] == 0:
             raise Exception("done")
         if a.ndim == 1:
             return a[:, np.newaxis]
         return a
 
 
-def main(readcsv=read_csv, method='defaultDense'):
+def main(readcsv=read_csv, method="defaultDense"):
     infile = "./data/batch/linear_regression_train.csv"
     testfile = "./data/batch/linear_regression_test.csv"
 
@@ -81,7 +84,7 @@ def main(readcsv=read_csv, method='defaultDense'):
     print("\nLinear Regression coefficients:\n", train_result.model.Beta)
     print(
         "\nLinear Regression prediction results: (first 10 rows):\n",
-        predict_result.prediction[0:10]
+        predict_result.prediction[0:10],
     )
     print("\nGround truth (first 10 rows):\n", ptdata[0:10])
-    print('All looks good!')
+    print("All looks good!")

examples/daal4py/low_order_moms_streaming.py

@@ -1,4 +1,4 @@
-#===============================================================================
+# ===============================================================================
 # Copyright 2014 Intel Corporation
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
@@ -12,32 +12,35 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-#===============================================================================
+# ===============================================================================
 
 # daal4py low order moments example for streaming on shared memory systems
 
-import daal4py as d4p
 import numpy as np
 
+import daal4py as d4p
+
 # let's try to use pandas' fast csv reader
 try:
     import pandas
 
     def read_csv(f, c, s=0, n=None, t=np.float64):
-        return pandas.read_csv(f, usecols=c, delimiter=',', header=None,
-                               skiprows=s, nrows=n, dtype=t)
+        return pandas.read_csv(
+            f, usecols=c, delimiter=",", header=None, skiprows=s, nrows=n, dtype=t
+        )
+
 except:
     # fall back to numpy genfromtxt
     def read_csv(f, c, s=0, n=np.iinfo(np.int64).max):
-        a = np.genfromtxt(f, usecols=c, delimiter=',', skip_header=s, max_rows=n)
+        a = np.genfromtxt(f, usecols=c, delimiter=",", skip_header=s, max_rows=n)
         if a.shape[0] == 0:
             raise Exception("done")
         if a.ndim == 1:
             return a[:, np.newaxis]
         return a
 
 
-def main(readcsv=read_csv, method='defaultDense'):
+def main(readcsv=read_csv, method="defaultDense"):
     # read data from file
     file = "./data/batch/covcormoments_dense.csv"
 
@@ -78,4 +81,4 @@ def main(readcsv=read_csv, method='defaultDense'):
     print("\nVariance:\n", res.variance)
     print("\nStandard deviation:\n", res.standardDeviation)
     print("\nVariation:\n", res.variation)
-    print('All looks good!')
+    print("All looks good!")